Adverse drug events caused by three high-risk drug-drug interactions in patients admitted to intensive care units: A multicentre retrospective observational study.

AIMS: Knowledge about adverse drug events caused by drug-drug interactions (DDI-ADEs) is limited. We aimed to provide detailed insights about DDI-ADEs related to three frequent, high-risk potential DDIs (pDDIs) in the critical care setting: pDDIs with international normalized ratio increase (INR+ ) potential, pDDIs with acute kidney injury (AKI) potential, and pDDIs with QTc prolongation potential. METHODS: We extracted routinely collected retrospective data from electronic health records of intensive care units (ICUs) patients (≥18 years), admitted to ten hospitals in the Netherlands between January 2010 and September 2019. We used computerized triggers (e-triggers) to preselect patients with potential DDI-ADEs. Between September 2020 and October 2021, clinical experts conducted a retrospective manual patient chart review on a subset of preselected patients, and assessed causality, severity, preventability, and contribution to ICU length of stay of DDI-ADEs using internationally prevailing standards. RESULTS: In total 85 422 patients with ≥1 pDDI were included. Of these patients, 32 820 (38.4%) have been exposed to one of the three pDDIs. In the exposed group, 1141 (3.5%) patients were preselected using e-triggers. Of 237 patients (21%) assessed, 155 (65.4%) experienced an actual DDI-ADE; 52.9% had severity level of serious or higher, 75.5% were preventable, and 19.3% contributed to a longer ICU length of stay. The positive predictive value was the highest for DDI-INR+ e-trigger (0.76), followed by DDI-AKI e-trigger (0.57). CONCLUSION: The highly preventable nature and severity of DDI-ADEs, calls for action to optimize ICU patient safety. Use of e-triggers proved to be a promising preselection strategy.

Adverse drug event detection using natural language processing: A scoping review of supervised learning methods.

To reduce adverse drug events (ADEs), hospitals need a system to support them in monitoring ADE occurrence routinely, rapidly, and at scale. Natural language processing (NLP), a computerized approach to analyze text data, has shown promising results for the purpose of ADE detection in the context of pharmacovigilance. However, a detailed qualitative assessment and critical appraisal of NLP methods for ADE detection in the context of ADE monitoring in hospitals is lacking. Therefore, we have conducted a scoping review to close this knowledge gap, and to provide directions for future research and practice. We included articles where NLP was applied to detect ADEs in clinical narratives within electronic health records of inpatients. Quantitative and qualitative data items relating to NLP methods were extracted and critically appraised. Out of 1,065 articles screened for eligibility, 29 articles met the inclusion criteria. Most frequent tasks included named entity recognition (n = 17; 58.6%) and relation extraction/classification (n = 15; 51.7%). Clinical involvement was reported in nine studies (31%). Multiple NLP modelling approaches seem suitable, with Long Short Term Memory and Conditional Random Field methods most commonly used. Although reported overall performance of the systems was high, it provides an inflated impression given a steep drop in performance when predicting the ADE entity or ADE relation class. When annotating corpora, treating an ADE as a relation between a drug and non-drug entity seems the best practice. Future research should focus on semi-automated methods to reduce the manual annotation effort, and examine implementation of the NLP methods in practice.

Machine learning models for predicting acute kidney injury: a systematic review and critical appraisal.

Background: The number of studies applying machine learning (ML) to predict acute kidney injury (AKI) has grown steadily over the past decade. We assess and critically appraise the state of the art in ML models for AKI prediction, considering performance, methodological soundness, and applicability. Methods: We searched PubMed and ArXiv, extracted data, and critically appraised studies based on the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD), Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS), and Prediction Model Risk of Bias Assessment Tool (PROBAST) guidelines. Results: Forty-six studies from 3166 titles were included. Thirty-eight studies developed a model, five developed and externally validated one, and three studies externally validated one. Flexible ML methods were used more often than deep learning, although the latter was common with temporal variables and text as predictors. Predictive performance showed an area under receiver operating curves ranging from 0.49 to 0.99. Our critical appraisal identified a high risk of bias in 39 studies. Some studies lacked internal validation, whereas external validation and interpretability of results were rarely considered. Fifteen studies focused on AKI prediction in the intensive care setting, and the US-derived Medical Information Mart for Intensive Care (MIMIC) data set was commonly used. Reproducibility was limited as data and code were usually unavailable. Conclusions: Flexible ML methods are popular for the prediction of AKI, although more complex models based on deep learning are emerging. Our critical appraisal identified a high risk of bias in most models: Studies should use calibration measures and external validation more often, improve model interpretability, and share data and code to improve reproducibility.

Volatile organic compound profiles in outlet air from extracorporeal life-support devices differ from breath profiles in critically ill patients.

INTRODUCTION: It is highly uncertain whether volatile organic compounds (VOCs) in exhaled breath of critically ill intensive care unit patients are formed in the lung locally, in the air compartment or lung tissue, or elsewhere in the body and transported to the lung via the bloodstream. We compared VOC mixtures in exhaled breath and in air coming from extracorporeal support devices in critically ill patients to address this issue. METHODS: First, we investigated whether it was safe to connect an electronic nose (eNose) or a gas sampling pump to extracorporeal support membranes. Then, breath and air from extracorporeal support devices were collected simultaneously for continuous monitoring of VOC mixtures using an eNose. In addition, samples for gas chromatography/mass spectrometry (GC-MS) analysis were taken daily at the two measurement sites. RESULTS: 10 critically ill patients were monitored for a median (interquartile range) duration of 73 (72-113) h; in total, we had 887 h of air sampling. The eNose signals of breath correlated moderately with signals of air from the extracorporeal support devices (R2=0.25-0.44). After GC-MS analysis, 96 VOCs were found both in breath and air from the extracorporeal support devices; of these, 29 (30%) showed a significant correlation (p<0.05) between the two measurement sites, of which 17 were identified. VOCs that did not correlate were found in a higher concentration in breath than in air from the extracorporeal support devices. CONCLUSION: This study suggests VOC analysis in the extracorporeal circulation is safe, and that VOCs of nonpulmonary origin can be measured in the breath and in the extracorporeal circulation of critically ill patients. For VOCs that did not correlate between the two measurement sites, the breath concentration was higher, suggesting pulmonary production of these molecules in a highly selected population of patients that received extracorporeal support.

Non-invasive breath monitoring with eNose does not improve glucose diagnostics in critically ill patients in comparison to continuous glucose monitoring in blood.

Continuous glucose monitoring (CGM) can be beneficial in critically ill patients. Current CGM devices rely on subcutaneous or blood plasma glucose measurements and consequently there is an increased risk of infections and the possibility of loss of blood with each measurement. A potential method to continuously and non-invasively measure blood glucose levels is using exhaled breath. A correlation between blood glucose levels and volatile organic compounds (VOCs) in the exhaled breath was already reported. VOCs can be analyzed continuously using a so-called electronic nose (eNose). We hypothesize that continuous exhaled breath analysis using an eNose can be used to accurately predict blood glucose levels in intubated, mechanically ventilated ICU-patients. Mechanically ventilated patients whose blood glucose concentration was monitored with a CGM device were eligible. An eNose with four metal oxide sensors was used to continuously measure changes in exhaled breath. After pre-processing the data, several regression models were trained, consisting of: (1) only eNose sensor values; (2) only the 1st and 2nd principal components (PC) of eNose values; (3) eNose sensor values and last known blood glucose value as random effect; (4) 1st and 2nd PC of eNose sensor values and CGM value of one minute ago as fixed effect; (5) CGM value of one minute ago as fixed effect. Model performance was measured using the R 2 value, the akaike information criterion and the Clarke error grid. Twenty-three patients were included in the study and 1165 hours of measurements were collected. Performance was low in models 1, 2 and 3 with a mean R 2 of 0.07 [95%-CI: 0.00-0.28], 0.10 [95%-CI: 0.00-0.40] and 0.30 [0.02-0.79], respectively. Performance in models 4 and 5 was better with a mean R 2 of 0.77 [0.02-1.00]. Subsequently, eNose data in model 4 had no added value over using CGM only in model 5. Continuous exhaled breath analysis using this eNose cannot be used to accurately predict blood glucose levels in intubated, mechanically ventilated ICU-patients.

Factors Influencing Continuous Breath Signal in Intubated and Mechanically-Ventilated Intensive Care Unit Patients Measured by an Electronic Nose.

INTRODUCTION: Continuous breath analysis by electronic nose (eNose) technology in the intensive care unit (ICU) may be useful in monitoring (patho) physiological changes. However, the application of breath monitoring in a non-controlled clinical setting introduces noise into the data. We hypothesized that the sensor signal is influenced by: (1) humidity in the side-stream; (2) patient-ventilator disconnections and the nebulization of medication; and (3) changes in ventilator settings and the amount of exhaled CO2. We aimed to explore whether the aforementioned factors introduce noise into the signal, and discuss several approaches to reduce this noise. METHODS: Study in mechanically-ventilated ICU patients. Exhaled breath was monitored using a continuous eNose with metal oxide sensors. Linear (mixed) models were used to study hypothesized associations. RESULTS: In total, 1251 h of eNose data were collected. First, the initial 15 min of the signal was discarded. There was a negative association between humidity and Sensor 1 (Fixed-effect ß: -0.05 ± 0.002) and a positive association with Sensors 2-4 (Fixed-effect ß: 0.12 ± 0.001); the signal was corrected for this noise. Outliers were most likely due to noise and therefore removed. Sensor values were positively associated with end-tidal CO2, tidal volume and the pressure variables. The signal was corrected for changes in these ventilator variables after which the associations disappeared. CONCLUSION: Variations in humidity, ventilator disconnections, nebulization of medication and changes of ventilator settings indeed influenced exhaled breath signals measured in ventilated patients by continuous eNose analysis. We discussed several approaches to reduce the effects of these noise inducing variables.

Comparison of classification methods in breath analysis by electronic nose.

Currently, many different methods are being used for pre-processing, statistical analysis and validation of data obtained by electronic nose technology from exhaled air. These various methods, however, have never been thoroughly compared. We aimed to empirically evaluate and compare the influence of different dimension reduction, classification and validation methods found in published studies on the diagnostic performance in several datasets. Our objective was to facilitate the selection of appropriate statistical methods and to support reviewers in this research area. We reviewed the literature by searching Pubmed up to the end of 2014 for all human studies using an electronic nose and methodological quality was assessed using the QUADAS-2 tool tailored to our review. Forty-six studies were evaluated regarding the range of different approaches to dimension reduction, classification and validation. From forty-six reviewed articles only seven applied external validation in an independent dataset, mostly with a case-control design. We asked their authors to share the original datasets with us. Four of the seven datasets were available for re-analysis. Published statistical methods for eNose signal analysis found in the literature review were applied to the training set of each dataset. The performance (area under the receiver operating characteristics curve (ROC-AUC)) was calculated for the training cohort (in-set) and after internal validation (leave-one-out cross validation). The methods were also applied to the external validation set to assess the external validity of the performance. Risk of bias was high in most studies due to non-random selection of patients. Internal validation resulted in a decrease in ROC-AUCs compared to in-set performance: -0.15,-0.14,-0.1,-0.11 in dataset 1 through 4, respectively. External validation resulted in lower ROC-AUC compared to internal validation in dataset 1 (-0.23) and 3 (-0.09). ROC-AUCs did not decrease in dataset 2 (+0.07) and 4 (+0.04). No single combination of dimension reduction and classification methods gave consistent results between internal and external validation sets in this sample of four datasets. This empirical evaluation showed that it is not meaningful to estimate the diagnostic performance on a training set alone, even after internal validation. Therefore, we recommend the inclusion of an external validation set in all future eNose projects in medicine.

Levels of cytokines in broncho-alveolar lavage fluid, but not in plasma, are associated with levels of markers of lipid peroxidation in breath of ventilated ICU patients.

Alkanes and alkenes in the breath are produced through fatty acid peroxidation, which is initialized by reactive oxygen species. Inflammation is an important cause and effect of reactive oxygen species. We aimed to evaluate the association between fatty acid peroxidation products and inflammation of the alveolar and systemic compartment in ventilated intensive care unit (ICU) patients.Volatile organic compounds were measured by gas chromatography and mass spectrometry in the breath of newly ventilated ICU patients within 24 h after ICU admission. Cytokines were measured in non-directed bronchial lavage fluid (NBL) and plasma by cytometric bead array. Correlation coefficients were calculated and presented in heatmaps.93 patients were included. Peroxidation products in exhaled breath were not associated with markers of inflammation in plasma, but were correlated with those in NBL. IL-6, IL-8, IL-1ß and TNF-α concentration in NBL showed inverse correlation coefficients with the peroxidation products of fatty acids. Furthermore, NBL IL-10, IL-13, GM-CSF and IFNγ demonstrated positive associations with breath alkanes and alkenes. Correlation coefficients for NBL cytokines were high regarding peroxidation products of n-6, n-7 and particularly in n-9 fatty acids.Levels of lipid peroxidation products in the breath of ventilated ICU patients are associated with levels of inflammatory markers in NBL, but not in plasma. Alkanes and alkenes in breath seems to be associated with an anti-inflammatory, rather than a pro-inflammatory state in the alveoli.

Point accuracy and reliability of an interstitial continuous glucose-monitoring device in critically ill patients: a prospective study.

INTRODUCTION: There is a need for continuous glucose monitoring in critically ill patients. The objective of this trial was to determine the point accuracy and reliability of a device designed for continuous monitoring of interstitial glucose levels in intensive care unit patients. METHODS: We evaluated point accuracy by comparing device readings with glucose measurements in arterial blood by using blood gas analyzers. Analytical and clinical accuracy was expressed in Bland-Altman plots, glucose prediction errors, and Clarke error grids. We used a linear mixed model to determine which factors affect the point accuracy. In addition, we determined the reliability, including duration of device start-up and calibration, skips in data acquisition, and premature disconnections of sensors. RESULTS: We included 50 patients in whom we used 105 sensors. Five patients from whom we could not collect the predefined minimum number of four consecutive comparative blood draws were excluded from the point accuracy analysis. Therefore, we had 929 comparative samples from 100 sensors in 45 patients (11 (7 to 28) samples per patient) during 4,639 hours (46 (27 to 134) hours per patient and 46 (21 to 69) hours per sensor) for the accuracy analysis. Point accuracy did not meet the International Organization for Standardization (ISO) 14971 standard for insulin dosing accuracy but did improve with increasing numbers of calibrations and was better in patients who did not have a history of diabetes. Out of 105 sensors, 60 were removed prematurely for a variety of reasons. The device start-up time was 49 (43 to 58) minutes. The number of skips in data acquisition was low, resulting in availability of real-time data during 95% (89% to 98%) of the connection time per sensor. CONCLUSIONS: The point accuracy of a device designed for continuous real-time monitoring of interstitial glucose levels was relatively low in critically ill patients. The device had few downtimes, but one third of the sensors were removed prematurely because of unresolved sensor- or device-related problems. TRIAL REGISTRATION: Netherlands Trial Registry number: NTR3827 . Registered 30 January 2013.

Glucose prediction by analysis of exhaled metabolites - a systematic review.

BACKGROUND: In critically ill patients, glucose control with insulin mandates time- and blood-consuming glucose monitoring. Blood glucose level fluctuations are accompanied by metabolomic changes that alter the composition of volatile organic compounds (VOC), which are detectable in exhaled breath. This review systematically summarizes the available data on the ability of changes in VOC composition to predict blood glucose levels and changes in blood glucose levels. METHODS: A systematic search was performed in PubMed. Studies were included when an association between blood glucose levels and VOCs in exhaled air was investigated, using a technique that allows for separation, quantification and identification of individual VOCs. Only studies on humans were included. RESULTS: Nine studies were included out of 1041 identified in the search. Authors of seven studies observed a significant correlation between blood glucose levels and selected VOCs in exhaled air. Authors of two studies did not observe a strong correlation. Blood glucose levels were associated with the following VOCs: ketone bodies (e.g., acetone), VOCs produced by gut flora (e.g., ethanol, methanol, and propane), exogenous compounds (e.g., ethyl benzene, o-xylene, and m/p-xylene) and markers of oxidative stress (e.g., methyl nitrate, 2-pentyl nitrate, and CO). CONCLUSION: There is a relation between blood glucose levels and VOC composition in exhaled air. These results warrant clinical validation of exhaled breath analysis to monitor blood glucose levels.